Johannes Gäßler 15d71189e9 CUDA: optimize and refactor MMQ (llama/8416) ...

* CUDA: optimize and refactor MMQ

* explicit q8_1 memory layouts, add documentation

2024-08-08 22:48:46 +03:00

..

ggml-cuda

CUDA: optimize and refactor MMQ (llama/8416)

2024-08-08 22:48:46 +03:00

ggml-sycl

Use multi_ptr to clean up deprecated warnings (llama/8256)

2024-08-08 22:48:46 +03:00

kompute-shaders

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

vulkan-shaders

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

CMakeLists.txt

ggml : move sgemm sources to llamafile subfolder (llama/8394)

2024-08-08 22:48:46 +03:00

ggml-alloc.c

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-backend-impl.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-backend.c

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-blas.cpp

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-common.h

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780)

2024-08-08 22:48:46 +03:00

ggml-cuda.cu

cuda : update supports_op for matrix multiplication (llama/8245)

2024-07-08 14:53:55 +03:00

ggml-impl.h

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780)

2024-08-08 22:48:46 +03:00

ggml-kompute.cpp

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-metal.m

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-metal.metal

Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (llama/8258)

2024-07-08 14:53:55 +03:00

ggml-quants.c

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780)

2024-08-08 22:48:46 +03:00

ggml-quants.h

Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (llama/8258)

2024-07-08 14:53:55 +03:00

ggml-rpc.cpp

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-sycl.cpp

sycl : Reenabled mmvq path for the SYCL Nvidia Backend (llama/8372)

2024-08-08 22:48:46 +03:00

ggml-vulkan-shaders.hpp

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

ggml-vulkan.cpp

vulkan : initialize vk_buffer_struct members to VK_NULL_HANDLE (ggml/893)

2024-08-08 22:48:46 +03:00

ggml.c

ggml : move sgemm sources to llamafile subfolder (llama/8394)

2024-08-08 22:48:46 +03:00

sgemm.cpp

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

sgemm.h

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00